Skip to content

Author

Marius Dima

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Open access Oct 2026

Certified Knowledge Editing: Closed-Form Reachability Guarantees for Additive Edits to a Frozen Language Model

Knowledge edits to language models are usually validated after the fact. This paper studies the reverse contract: a closed-form certificate, computed before an edit is applied, of exactly which single-token edits can succeed on a frozen decoder-only language model with an additive gated memory. The certificate reduces...

Marius Dima · 0 citations
#small language model Open access Oct 2026

Certified Knowledge Editing: Closed-Form Reachability Guarantees for Additive Edits to a Frozen Language Model

Knowledge edits to language models are usually validated after the fact. This paper studies the reverse contract: a closed-form certificate, computed before an edit is applied, of exactly which single-token edits can succeed on a frozen decoder-only language model with an additive gated memory. The certificate reduces...

Marius Dima · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.